© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77820
    Prev
    Next
    INDEX
    Explanations

    technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.73
    enment
    -0.62
    PerformLayout
    -0.60
    DidLoad
    -0.59
     gu
    -0.57
    HtmlAttribute
    -0.56
     viewDidLoad
    -0.56
    FundMe
    -0.55
    UserScript
    -0.55
     gynnwys
    -0.54
    POSITIVE LOGITS
     propOrder
    0.71
    GraphicsUnit
    0.64
     مشين
    0.61
    An
    0.59
     An
    0.59
     transfieras
    0.57
     Crit
    0.56
    كويكب
    0.54
    crites
    0.53
     Ana
    0.53
    Activations Density 0.000%

    No Known Activations